ECloudGen: leveraging electron clouds as a latent variable to scale up structure-based molecular design.

Abstract

Structure-based molecule generation represents a notable advancement in artificial intelligence-driven drug design. However, progress in this field is constrained by the scarcity of structural data on protein-ligand complexes. Here we propose a latent variable approach that bridges the gap between ligand-only data and protein-ligand complexes, enabling target-aware generative models to explore a broader chemical space, thereby enhancing the quality of molecular generation. Inspired by quantum molecular simulations, we introduce ECloudGen, a generative model that leverages electron clouds as meaningful latent variables. ECloudGen incorporates techniques such as latent diffusion models, Llama architectures and a contrastive learning task, which organizes the chemical space into a structured and highly interpretable latent representation. Benchmark studies demonstrate that ECloudGen outperforms state-of-the-art methods by generating more potent binders with superior physiochemical properties and by covering a broader chemical space. The incorporation of electron clouds as latent variables not only improves generative performance but also introduces model-level interpretability, as illustrated in our case studies.